INDEX

Explanations

high/low

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ue

-0.25

ni

-0.24

æİī

-0.24

è¡¬è¡«

-0.24

æ±½è½¦è¡Įä¸ļ

-0.24

uer

-0.24

lickr

-0.23

sector

-0.23

å½ĵä¹ĭ

-0.23

idad

-0.23

POSITIVE LOGITS

åıģ

0.30

isel

0.28

æĬ½åıĸ

0.27

 isolation

0.25

 itemType

0.25

äºĴçĽ¸

0.24

 diligence

0.23

ë¥Ļ

0.23

äººåĿĩ

0.23

ç¨ł

0.23

Activations Density 0.007%

high/low

No Comments

No Known Activations